IP Library › Granted Patent US 12,491,436
Granted Patent B2
US 12,491,436 · App. 18/228,548 · Granted Dec 9, 2025

Virtual assistant for game discovery

Inventors: Chen Yao (Bloomingdale, IL); Jun Murakawa (Foster City, CA); Sagnik Chowdhury (San Jose, CA); Ratnakar Pawar (Redwood City, CA); Robert Brown (Lafayette, CA)
Assignee: Sony Interactive Entertainment Inc.
A63F13/5375G10L15/22
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,491,436
App. No.
18/228,548
Granted
Dec 9, 2025
Kind
B2
Abstract

A device, system, and non-transitory computer readable medium for providing a specialized agent comprising an application and a virtual assistant are disclosed. The virtual assistant includes a neural network trained with a machine learning algorithm to emulate a communication style of a character and wherein the virtual assistant is further trained on application metadata to a predict response to questions about the application.

Claims (34)

1 . A device for providing a specialized agent comprising;

a video game application; and

a virtual assistant configured to predict a response to a question about the video game application received by the device, wherein the virtual assistant comprises a neural network trained with a machine learning algorithm to emulate a communication style of a video game character associated the video game application, and wherein the virtual assistant is further configured to validate the response based on whether the response includes a video game spoiler.

2 . The device of claim 1 , wherein the virtual assistant further comprises a natural language processing module operable to convert language input into a computer readable form.

3 . The device of claim 1 , wherein the virtual assistant further comprises a text to speech module operable to convert text responses from the virtual assistant to speech.

4 . The device of claim 3 , wherein the text to speech module includes a speech neural network trained with a machine learning algorithm to replicate a speech style of a character.

5 . The device of claim 4 , wherein the speech neural network is trained to replicate the speech style by replicating one or more of a group of intonation, speed, pronunciation, and prosody.

6 . The device of claim 3 , wherein the text to speech module includes a speech neural network trained with a machine learning algorithm on voice recordings.

7 . The device of claim 1 , wherein the virtual assistant further comprises a gameplay module, wherein the gameplay module is operable to operate the video game application.

8 . The device of claim 7 , wherein the video game application is operable to allow the gameplay module to operate in tandem with a user.

9 . The device of claim 7 , wherein the video game application is configured to enable cooperative game and the gameplay module is operable to play cooperatively with a user.

10 . The device of claim 7 , wherein the gameplay module includes a neural network trained with a machine learning to operate the video game application.

11 . The device of claim 1 , the virtual assistant further comprises a negative representation module operable to detect that the response comprises a negative representation, wherein the negative representation comprises false information, misleading information, inappropriate information, or a combination thereof, and to remove the negative representation upon detecting the negative representation.

12 . The device of claim 11 , wherein the negative representation module includes a representation neural network trained with a machine learning algorithm configured to detect the negative representation.

13 . The device of claim 11 , wherein the negative representation module includes a representation neural network trained with a machine learning algorithm configured to detect that the response comprises the video game spoiler, wherein the video game spoiler comprises information for a part of the video game application a user has not seen yet.

14 . The device claim 1 , wherein the virtual assistant further comprises a character module wherein the character module is operable to coordinate a visual display of the video game character with the response to question.

15 . The device of claim 1 , wherein the virtual assistant further comprises a video module, wherein the video module is operable to retrieve a video based on the response.

16 . The device of claim 1 , wherein the virtual assistant further comprises a video module, wherein the video module is operable to overlay video and/or text and/or graphic content on top of image frames of the application.

17 . A system for providing a specialized agent comprising:

a processor;

a memory coupled to the processor;

non-transitory processor executable instructions embodied in the memory that when executed by the processor causes the processor to carry out a method comprising:

executing a video game application; and

providing a response to a question from a user about the video game application, wherein the response is generated by a virtual assistant, wherein the virtual assistant comprises a neural network trained with a machine learning algorithm to emulate a communication style of a video game character associated with the video game application and, wherein providing the response comprises validating the response based on whether the response includes a video game spoiler.

18 . The system of claim 17 , wherein the non-transitory processor executable instructions further include converting the question from a non-computer readable format to a computer readable format with a natural language processing neural network wherein the natural language processing neural network is communicatively coupled with the virtual assistant.

19 . The system of claim 17 , wherein the non-transitory processor executable instructions further include one or more instructions that when executed by the processor causes the processor to convert the response to the question from the user to speech using a text to speech module.

20 . The system of claim 19 , wherein the text to speech module includes a speech neural network trained with a machine learning algorithm to replicate a speech style of a character.

21 . The system of claim 20 , wherein the speech neural network is trained to replicate the speech style of the character by replicating one or more of a group of intonation, speed, pronunciation, and prosody.

22 . The system of claim 20 , wherein the speech neural network trained is with a machine learning algorithm using voice recordings.

23 . The system of claim 17 , wherein the non-transitory processor executable instructions further include one or more instructions that when executed by the processor causes the processor to operate the video game application to provide the response to the question from the user using a gameplay module.

24 . The system of claim 23 , wherein the video game application is operable to allow the gameplay module to operate in tandem with the user.

25 . A method comprising:

executing a video game application; and

providing a response to a question from a user about the video game application, wherein the response is generated by a virtual assistant comprising a neural network trained with a machine learning algorithm to emulate a communication style of a video game character associated with the video game application, and wherein providing the response comprises validating the response based on whether the response includes, a video game spoiler.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 31, 2023
From: YAO, CHEN; MURAKAWA, JUN; CHOWDHURY, SAGNIK; PAWAR, RATNAKAR; BROWN, ROBERT
To: SONY INTERACTIVE ENTERTAINMENT INC.
Reel/Frame 064768/0390 →
Continuity (1)
Related Publication 20250041724A1 · Feb 6, 2025
References Cited (69)
US 6352479B1 · Sparks · 2002 [cited by applicant]
US 8515253B2 · Cottrell · 2013 [cited by applicant]
US 9364743B2 · Miura et al. · 2016 [cited by applicant]
US 9457264B1 · Chyou et al. · 2016 [cited by applicant]
US 9630097B2 · Paradise et al. · 2017 [cited by applicant]
US 9782678B2 · Long et al. · 2017 [cited by applicant]
US 10335690B2 · Schleicher · 2019 [cited by applicant]
US 10456680B2 · Miron et al. · 2019 [cited by applicant]
US 11071910B1 · Landers et al. · 2021 [cited by applicant]
US 11338210B2 · Benedetto et al. · 2022 [cited by applicant]
US 12045638B1 · Gu · 2024 [cited by examiner]
US 20010016510A1 · Ishikawa et al. · 2001 [cited by applicant]
US 20060046234A1 · Sperry · 2006 [cited by applicant]
US 20110246621A1 · May et al. · 2011 [cited by applicant]
US 20110269540A1 · Gillo et al. · 2011 [cited by applicant]
US 20120202594A1 · Bistis et al. · 2012 [cited by applicant]
US 20130079134A1 · Walker et al. · 2013 [cited by applicant]
US 20130249947A1 · Reitan · 2013 [cited by applicant]
US 20130260894A1 · Graf et al. · 2013 [cited by applicant]
US 20140038701A1 · Allen et al. · 2014 [cited by applicant]
US 20140162780A1 · Suzuki · 2014 [cited by applicant]
US 20140258469A1 · Maharajh et al. · 2014 [cited by applicant]
US 20140278686A1 · Mullings et al. · 2014 [cited by applicant]
US 20150157938A1 · Domansky et al. · 2015 [cited by applicant]
US 20150231502A1 · Allen et al. · 2015 [cited by applicant]
US 20160255409A1 · Feldstein et al. · 2016 [cited by applicant]
US 20170064014A1 · Nomura · 2017 [cited by applicant]
US 20170087460A1 · Perry · 2017 [cited by applicant]
US 20170259177A1 · Aghdaie et al. · 2017 [cited by applicant]
US 20180365935A1 · Howell et al. · 2018 [cited by applicant]
US 20200061465A1 · Benedetto et al. · 2020 [cited by applicant]
US 20200122031A1 · Sherwani et al. · 2020 [cited by applicant]
US 20200139245A1 · Jarzebinski · 2020 [cited by applicant]
US 20200289932A1 · Benedetto et al. · 2020 [cited by applicant]
US 20210038998A1 · Tallarico et al. · 2021 [cited by applicant]
US 20210086089A1 · Pardeshi et al. · 2021 [cited by applicant]
US 20210146241A1 · Bleasdale-Shepherd et al. · 2021 [cited by applicant]
US 20210151034A1 · Hasan et al. · 2021 [cited by applicant]
US 20210173548A1 · Brown et al. · 2021 [cited by applicant]
US 20210213353A1 · Berg et al. · 2021 [cited by applicant]
US 20210370183A1 · Dorn et al. · 2021 [cited by applicant]
US 20220019744A1 · Yu et al. · 2022 [cited by applicant]
US 20220096937A1 · Dorn et al. · 2022 [cited by applicant]
US 20230031521A1 · Anders et al. · 2023 [cited by applicant]
US 20230078380A1 · Zaghetto et al. · 2023 [cited by applicant]
US 20230206574A1 · Whitney et al. · 2023 [cited by applicant]
US 20230376328A1 · Nagar · 2023 [cited by examiner]
US 20240036636A1 · Press · 2024 [cited by examiner]
US 20240202285A1 · Dechu · 2024 [cited by examiner]
US 20240289686A1 · Desgarennes · 2024 [cited by examiner]
US 20240290329A1 · Dasher · 2024 [cited by examiner]
US 20240412030A1 · Guinn · 2024 [cited by examiner]
US 20250036889A1 · Fu · 2025 [cited by examiner]
WO 2014100770A2 · 2014 [cited by applicant]
WO 2019182680A1 · 2019 [cited by applicant]
WO 2021156848A1 · 2021 [cited by applicant]
U.S. Appl. No. 18/208,159 to Rathish Krishnan et al. filed Jun. 9, 2023. [cited by applicant]
U.S. Appl. No. 18/208,166 to Chen Yao et al. filed Jun. 9, 2023. [cited by applicant]
U.S. Appl. No. 18/208,179 to Chen Yao et al. filed Jun. 9, 2023. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2024/030758, dated Aug. 15, 2024. [cited by applicant]
International Search Report dated Aug. 13, 2024 for International Patent Application No. PCT/US2024/030760. [cited by applicant]
Clark et al. “ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators” ArXiv abs/2003. 10555, 2020. [cited by applicant]
D. Sasirekha et al. “Text to Speech: A simple Tutorial” Int. J. of Sort Computing and Eng. (IJSCE) vol. 2 Iss. 1 Mar. 2012 ISSN: 2231-2307. [cited by applicant]
Dutoit, Thierry “High Quality Text to Speech Synthesis: An Overview” Faculte Polyechnique de Mons, TCTS lab, 1997. [cited by applicant]
Fuzhen Zhuang et al. “A Comprehensive Survey on Transfer Learning” In Proceedings of the IEEE, vol. 109, No. 1, pp. 43-76, Jan. 2021. [cited by applicant]
Hochreiter & Schmidhuber “Long Short-term memory” Neural Computation 9(8):1735-1780 (1997). [cited by applicant]
Nadkarni et al. “Natural Language Processing: an introduction” J. Am. Med. Assoc. 2011; 18:544-551 accessed Jun. 27, 2023. [cited by applicant]
Radford et al. “Improving Language Understanding by Generative Pre-training” Open AI, Jun. 2018. [cited by applicant]
Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N.; Kaiser, Lukasz; Polosukhin, Illia (Dec. 5, 2017). “Attention Is All You Need”. arXiv:1706.03762. [cited by applicant]